Prognosis Prediction of Stroke based on Machine Learning and Explanation Model

Abstract

The prognosis prediction of stroke is of great significance to its prevention and treatment. This paper used machine learning to predict stroke prognosis, and use SHAP method to make feature importance and single sample analysis. Firstly, feature engineering, use Borderline-SMOTE algorithm to deal with data imbalance, use Support Vector Machine(SVM) to build a prognostic prediction model, and use Random Forest(RF), Decision Tree(DT), Logistic Regression(LR) for comparative analysis, and find the performance of SVM after feature engineering better than other models, the accuracy, specificity, F1 score, AUC value reach 0.8306, 0.8356, 0.8415 and 0.9140. Then, the model was further analyzed for explainability, and it was found that the top three causes of the disease were Glasgow Coma Score, NIHSS and atrial fibrillation. Finally, try to analysis a single sample, which is performed to determine that the patient is a low-risk patient, and suffering from atrial fibrillation is the largest potential risk factor for the patient.